Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Diluted / not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Use
    0.52
     Use
    0.50
     Declare
    0.45
     Free
    0.43
    Calculate
    0.40
     উপযুক্ত
    0.38
     forces
    0.38
     Multi
    0.38
     Calculate
    0.38
     Innovative
    0.38
    POSITIVE LOGITS
    зви
    0.45
     pi
    0.43
     начиная
    0.43
     рода
    0.42
     соци
    0.41
     rade
    0.41
     pname
    0.40
     fname
    0.39
    ради
    0.39
    めでとう
    0.39
    Act Density 0.000%

    No Known Activations